Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    catal

    np_max-act · gemini-2.0-flash

    The neuron detects references to catalysis, i.e. words or word parts related to “catalyst,” “catalyze,” “catalytic,” and similar forms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thư
    -0.07
    ufe
    -0.06
     �
    -0.06
    Blood
    -0.06
     İlk
    -0.06
     ansch
    -0.06
     leaps
    -0.06
    鸟
    -0.06
    nees
    -0.06
    "?
    -0.06
    POSITIVE LOGITS
     catal
    0.13
     Catal
    0.11
     Catalan
    0.08
     Catalonia
    0.08
     necess
    0.07
    atal
    0.07
     позвол
    0.07
    stal
    0.07
    	glColor
    0.07
     attenu
    0.07
    Act Density 0.005%

    No Known Activations